CN113180596A - Non-contact sleep analysis method and device and storage medium - Google Patents
Non-contact sleep analysis method and device and storage medium Download PDFInfo
- Publication number
- CN113180596A CN113180596A CN202110372729.1A CN202110372729A CN113180596A CN 113180596 A CN113180596 A CN 113180596A CN 202110372729 A CN202110372729 A CN 202110372729A CN 113180596 A CN113180596 A CN 113180596A
- Authority
- CN
- China
- Prior art keywords
- signals
- respiratory
- signal
- sleep
- features
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000007958 sleep Effects 0.000 title claims abstract description 77
- 238000004458 analytical method Methods 0.000 title claims abstract description 71
- 230000000241 respiratory effect Effects 0.000 claims abstract description 102
- 230000029058 respiratory gaseous exchange Effects 0.000 claims abstract description 76
- 230000000747 cardiac effect Effects 0.000 claims abstract description 46
- 230000002159 abnormal effect Effects 0.000 claims abstract description 30
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 18
- 230000003044 adaptive effect Effects 0.000 claims abstract description 13
- 208000008784 apnea Diseases 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 230000033001 locomotion Effects 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 12
- 238000000513 principal component analysis Methods 0.000 claims description 12
- 201000002859 sleep apnea Diseases 0.000 claims description 10
- 210000000115 thoracic cavity Anatomy 0.000 claims description 10
- 210000000038 chest Anatomy 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000005192 partition Methods 0.000 claims description 6
- 238000007637 random forest analysis Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000036387 respiratory rate Effects 0.000 abstract description 10
- 230000000694 effects Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 230000008667 sleep stage Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 230000037053 non-rapid eye movement Effects 0.000 description 3
- 210000003403 autonomic nervous system Anatomy 0.000 description 2
- 210000000748 cardiovascular system Anatomy 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000003860 sleep quality Effects 0.000 description 2
- RAFGELQLHMBRHD-VFYVRILKSA-N Bixin Natural products COC(=O)C=CC(=C/C=C/C(=C/C=C/C=C(C)/C=C/C=C(C)/C=C/C(=O)O)/C)C RAFGELQLHMBRHD-VFYVRILKSA-N 0.000 description 1
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 206010021133 Hypoventilation Diseases 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- RAFGELQLHMBRHD-UHFFFAOYSA-N alpha-Fuc-(1-2)-beta-Gal-(1-3)-(beta-GlcNAc-(1-6))-GalNAc-ol Natural products COC(=O)C=CC(C)=CC=CC(C)=CC=CC=C(C)C=CC=C(C)C=CC(O)=O RAFGELQLHMBRHD-UHFFFAOYSA-N 0.000 description 1
- 239000001670 anatto Substances 0.000 description 1
- 235000012665 annatto Nutrition 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- RAFGELQLHMBRHD-SLEZCNMESA-N bixin Chemical compound COC(=O)\C=C\C(\C)=C/C=C/C(/C)=C/C=C/C=C(\C)/C=C/C=C(\C)/C=C/C(O)=O RAFGELQLHMBRHD-SLEZCNMESA-N 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 208000014486 central sleep apnea syndrome Diseases 0.000 description 1
- 210000003710 cerebral cortex Anatomy 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 208000035475 disorder Diseases 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 210000003016 hypothalamus Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000001797 obstructive sleep apnea Diseases 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000013186 photoplethysmography Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004461 rapid eye movement Effects 0.000 description 1
- 208000019116 sleep disease Diseases 0.000 description 1
- 208000020685 sleep-wake disease Diseases 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02405—Determining heart rate variability
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/0245—Detecting, measuring or recording pulse rate or heart rate by using sensing means generating electric signals, i.e. ECG signals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
- A61B5/0816—Measuring devices for examining respiratory frequency
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4812—Detecting sleep stages or cycles
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Abstract
The invention discloses a non-contact sleep analysis method, a non-contact sleep analysis device and a storage medium, wherein the method comprises the following steps: receiving an echo signal, and eliminating a direct current component and an abnormal human body signal in the echo signal to obtain a signal containing the direct current component and the abnormal human body signal; performing adaptive noise complete set empirical mode decomposition on the superposed signals to obtain respiratory signals and cardiac signals; dividing the respiration signal and the cardiac signal into a plurality of sections according to a preset time interval to obtain signal samples; calculating a respiration variability characteristic and a heart rate variability characteristic according to the signal samples; performing dimension reduction on the respiratory variability feature and the heart rate variability feature to obtain an optimal feature set; and inputting the optimal feature set into a preset division model and a preset breathing model to obtain a sleep analysis result of the user. By adopting the embodiment of the invention, the heart rate and the respiratory rate are extracted in a non-contact way, and the accuracy of sleep analysis is improved.
Description
Technical Field
The present invention relates to the field of sleep monitoring, and in particular, to a non-contact sleep analysis method, device and storage medium.
Background
Sleep quality monitoring is an important direction in the field of intelligent medical treatment, sleep stages are important methods for evaluating sleep quality, and according to the american society of sleep medicine, sleep stages are generally interpreted as a wake stage (W stage), a non-rapid eye movement 1 stage (N1 stage), a non-rapid eye movement 2 stage (N2 stage), a non-rapid eye movement 3 stage (N3 stage), and a rapid eye movement stage (R stage). The frequent abnormal respiratory events in sleep are also the key points of sleep monitoring, and the sleep disordered breathing can be classified into obstructive sleep apnea, central sleep apnea syndrome and sleep-related alveolar hypoventilation disorder according to the international classification of the sleep disorder. The detection of the sleep abnormal respiratory event provides early warning for heart diseases and cerebral apoplexy.
The heart rate signal and the respiration signal are two most important signals in sleep monitoring, the autonomic nervous system is dominated by cerebral cortex and hypothalamus, the autonomic nervous system dominates a cardiovascular system, the cardiovascular system governs the regulation and control of respiration, and the activity of brain electricity of people can be reflected on the activity of heart and respiration. The time domain, frequency domain and non-linear domain characteristics of Heart Rate Variability (HRV) extracted from heart rate signals, and respiratory variability (RRV) extracted from respiratory rate are significant for sleep stages and sleep behavior abnormalities.
Traditional sleep staging, abnormal breathing event detection uses polysomnography, whose contact use characteristics cause discomfort to the user. In addition, the electrocardiograph and the finger clip oximeter using the photoplethysmography need to be used in a contact manner, and are not suitable for monitoring newborn, severely burned patients and patients in sleeping scenes.
Disclosure of Invention
The embodiment of the invention provides a non-contact sleep analysis method, a non-contact sleep analysis device and a non-contact sleep analysis storage medium, wherein heart rate and respiratory rate are extracted and analyzed in a non-contact manner, characteristic values of heart rate variability and respiratory variability are extracted and are simultaneously input into a division model and a respiratory model, and the sleep analysis accuracy is improved.
A first aspect of an embodiment of the present application provides a non-contact sleep analysis method, including: receiving echo signals, and eliminating direct current components and abnormal human body signals in the echo signals to obtain superposed signals containing human body chest signals and heart front and back movement signals; the echo signal is obtained by transmitting an electromagnetic wave to the position of the thoracic cavity of the human body of the user by using an ultra-wideband radar;
performing adaptive noise complete set empirical mode decomposition on the superposed signals to obtain respiratory signals and cardiac signals;
dividing the respiratory signal and the cardiac signal into a plurality of sections according to a preset time interval to obtain a signal sample containing a plurality of sections of respiratory signals and a plurality of sections of cardiac signals;
calculating respiratory variability features corresponding to the multiple segments of respiratory signals and heart rate variability features corresponding to the multiple segments of cardiac signals according to the signal samples;
performing dimension reduction on the respiratory variability feature and the heart rate variability feature to obtain an optimal feature set;
inputting the optimal feature set into a preset division model and a preset breathing model to obtain a sleep analysis result of the user; the sleep analysis result comprises sleep period division, abnormal sleep breathing state analysis and abnormal sleep breathing type analysis.
In a possible implementation manner of the first aspect, the calculating, according to the signal samples, a respiration variability characteristic corresponding to the multiple segments of respiration signals and a heart rate variability characteristic corresponding to the multiple segments of cardiac signals specifically includes:
calculating a BB interval of each segment of the respiratory signal and an HH interval of each segment of the cardiac signal in the signal sample; the BB interval refers to the time difference between adjacent peaks of the respiratory signal; the HH interval refers to a time difference between adjacent peaks of the cardiac signal;
obtaining respiratory variability features corresponding to the multiple respiratory signals according to BB intervals of the multiple respiratory signals;
and obtaining heart rate variability characteristics corresponding to the multiple segments of cardiac signals according to the HH intervals of the multiple segments of cardiac signals.
In one possible implementation form of the first aspect, the respiratory variability feature comprises a time domain, a frequency domain, a non-linear domain feature of respiratory variability; the heart rate variability features include time domain, frequency domain, nonlinear domain features of heart rate variability.
In a possible implementation manner of the first aspect, the receiving an echo signal, eliminating a direct current component and an abnormal human body signal in the echo signal, and obtaining a superimposed signal including a human chest signal and a heart front-back movement signal specifically includes:
subtracting the echo signal from an average of the echo signal;
and carrying out data cleaning on the echo signals, and if the amplitude of part of the signals in the echo signals is larger than a preset filling threshold, randomly filling the part of the signals exceeding the threshold.
In a possible implementation manner of the first aspect, the performing adaptive noise complete set empirical mode decomposition on the superimposed signal to obtain a respiratory signal and a cardiac signal specifically includes:
performing adaptive noise complete set empirical mode decomposition on the superposed signals, and selecting signal components to extract respiratory signals;
the respiration signal is subtracted from the echo signal, and a heart rate signal is extracted using an adaptive sliding energy time window.
In a possible implementation manner of the first aspect, the reducing dimensions of the respiratory variability feature and the heart rate variability feature to obtain an optimal feature set specifically includes:
performing cross entropy analysis on the heart rate variability features and the respiration variability features to obtain similar features;
removing the similar features between the heart rate variability feature and the respiration variability feature resulting in a remaining feature;
and performing principal component analysis on the remaining features according to a KL divergence formula to obtain an optimal feature set.
In a possible implementation manner of the first aspect, the establishing process of the partitioning model is:
calling an electrocardio annotation file, a breath annotation file, an apnea annotation file and a sleep apnea annotation file in the MIT data set;
according to the electrocardio annotation file, the respiration annotation file, the apnea annotation file, the sleep apnea annotation file and a preset division interval, carrying out time re-division on the MIT data set, and dividing the MIT data set into a plurality of sections of data with sleep apnea labels or apnea labels; the length of each segment of data is the same as the division interval;
calculating time domain, frequency domain and nonlinear domain characteristics of the electrocardiosignals and the respiration signals in the MIT data set, and constructing a characteristic set for division;
measuring the similarity between the features in the divided feature set by using cross entropy, if the similarity between the two features exceeds a first similarity threshold, reserving one of the two features, and then performing principal component analysis on the divided feature set;
dividing the division characteristic set into a division training set and a division testing set;
and training the division training set by using machine learning algorithms of a hidden Markov model, a random forest and a CNN respectively, and performing weighted judgment on a result output by each machine learning algorithm by using a soft voting mode to obtain the division model.
In a possible implementation manner of the first aspect, the process of establishing the breathing model is:
calling a breath annotation file and an apnea annotation file in the MIT data set;
according to the breathing interval preset by the breathing annotation file and the apnea annotation file, time subdivision is carried out on the MIT data set, the MIT data set is divided into multiple sections of data with apnea labels, and the length of each section of data is the same as that of the breathing interval;
calculating time domain, frequency domain and nonlinear domain characteristics of the breathing signals in the MIT data set, and constructing a breathing characteristic set;
measuring the similarity between the features in the respiratory feature set by using cross entropy, if the similarity between the two features exceeds a second similarity threshold, reserving one of the two features, and then performing principal component analysis on the respiratory feature set;
dividing the respiratory feature set into a respiratory training set and a respiratory testing set;
and training the breathing training set by using machine learning algorithms of a hidden Markov model, a random forest and a CNN respectively, and performing weighted judgment on a result output by each machine learning algorithm by using a soft voting mode to obtain the breathing model.
A second aspect of an embodiment of the present application provides a non-contact sleep analysis apparatus, including:
the receiving module is used for receiving the echo signals, eliminating direct current components and abnormal human body signals in the echo signals and obtaining superposed signals containing human body chest signals and heart front and back movement signals; the echo signal is obtained by transmitting an electromagnetic wave to the position of the thoracic cavity of the human body of the user by using an ultra-wideband radar;
the decomposition module is used for carrying out self-adaptive noise complete set empirical mode decomposition on the superposed signals to obtain respiratory signals and cardiac signals;
the dividing module is used for dividing the respiratory signal and the cardiac signal into a plurality of sections according to a preset time interval to obtain a signal sample containing the plurality of sections of respiratory signals and the plurality of sections of cardiac signals;
the extraction module is used for calculating respiratory variability features corresponding to the multiple segments of respiratory signals and heart rate variability features corresponding to the multiple segments of cardiac signals according to the signal samples;
the dimension reduction module is used for reducing dimensions of the respiratory variability feature and the heart rate variability feature to obtain an optimal feature set;
the analysis module is used for inputting the optimal feature set into a preset division model and a preset breathing model to obtain a sleep analysis result of the user; the sleep analysis result comprises sleep period division, abnormal sleep breathing state analysis and abnormal sleep breathing type analysis.
A third aspect of the embodiments of the present application provides a computer-readable storage medium, which includes a stored computer program, where when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute the method for non-contact sleep analysis according to the above embodiments.
Compared with the prior art, the non-contact sleep analysis method, the non-contact sleep analysis device and the storage medium provided by the embodiment of the invention capture the thoracic cavity movement of a human body caused by breathing and heartbeat in a non-contact manner by using the ultra-wideband radar, extract the initial heart rate and the breathing signal, detect the respiratory abnormal event by using the breathing signal, and detect the sleep stage and the respiratory abnormal event by using the Heart Rate Variability (HRV) and the Respiratory Rate Variability (RRV) to obtain the sleep analysis result.
Before sleep analysis is carried out, the relative entropy analysis and the principal component analysis are utilized to carry out dimensionality reduction on heart rate variability and respiratory rate variability characteristics, reduce training characteristics and improve the calculation rate; in the sleep analysis process, a feature set formed by the heart rate variability and the respiratory rate variability is input into the partition model and the respiratory model, so that the accuracy of the sleep analysis is improved.
Drawings
Fig. 1 is a schematic flow chart of a non-contact sleep analysis method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a respiratory model and a partition model establishment according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a non-contact sleep analysis method according to an embodiment of the present invention includes:
s10, receiving echo signals, eliminating direct current components and abnormal human body signals in the echo signals, and obtaining superposed signals containing human body chest cavity signals and heart front and back movement signals; the echo signal is obtained by transmitting an electromagnetic wave to the position of the thoracic cavity of the human body of the user by using an ultra-wideband radar.
S11, performing self-adaptive noise complete set empirical mode decomposition on the superposed signals to obtain respiratory signals and cardiac signals;
and S12, dividing the respiratory signal and the cardiac signal into a plurality of sections according to a preset time interval to obtain signal samples containing the plurality of sections of respiratory signals and the plurality of sections of cardiac signals.
And S13, calculating respiratory variability features corresponding to the multiple respiratory signals and heart rate variability features corresponding to the multiple cardiac signals according to the signal samples.
And S14, performing dimension reduction on the respiratory variability feature and the heart rate variability feature to obtain an optimal feature set.
S15, inputting the optimal feature set into a preset division model and a preset breathing model to obtain a sleep analysis result of the user; the sleep analysis result comprises sleep period division, abnormal sleep breathing state analysis and abnormal sleep breathing type analysis.
In practical application, the ultra-wideband radar is generally placed under a bed and aligned with the chest cavity of a person in a sleeping posture. The abnormal human body signal in S10 includes a body motion signal.
The division model and the breathing model are equivalent to a classifier, and the classifier classifies the optimal feature set formed by the HRV features and the BRV features, so that the accuracy of sleep analysis is improved.
The embodiment captures the thoracic cavity movement of a human body caused by breathing and heartbeat in a non-contact manner by using the ultra-wideband radar, extracts the initial heart rate and the breathing signal, detects the respiratory abnormal event by using the breathing signal, and detects the sleep stage and the respiratory abnormal event by using the Heart Rate Variability (HRV) and the Respiratory Rate Variability (RRV) to obtain the sleep analysis result.
Before sleep analysis is carried out, the relative entropy analysis and the principal component analysis are utilized to carry out dimensionality reduction on heart rate variability and respiratory rate variability characteristics, reduce training characteristics and improve the calculation rate; in the sleep analysis process, a feature set formed by the heart rate variability and the respiratory rate variability is input into the partition model and the respiratory model, so that the accuracy of the sleep analysis is improved.
Exemplarily, S10 specifically includes:
and S100, subtracting the average value of the echo signals from the echo signals.
S101, data cleaning is carried out on the echo signals, and if the amplitude of part of the echo signals is larger than a preset filling threshold value, random filling is carried out on the part of the echo signals exceeding the threshold value.
The average value of the echo signals is subtracted in S100, so that direct current components in the echo signals can be effectively eliminated, and the echo signals are subjected to data cleaning in S101, so that large-amplitude noise caused by body motion can be eliminated.
It should be noted that randomly filling the part of the signal exceeding the threshold will not affect the empirical mode decomposition and the sliding energy window, but may cause the respiratory decision to decide that the segment is an apnea, so that the subsequent decision time of the apnea may take this effect into consideration.
Exemplarily, S11 specifically includes:
s110, performing self-adaptive noise complete set empirical mode decomposition on the superposed signals, and selecting signal components to extract respiratory signals;
and S111, subtracting the respiration signal from the echo signal, and extracting a heart rate signal by using an adaptive sliding energy time window.
Performing adaptive noise complete set empirical mode decomposition (CEEMD) decomposition on the signals, and selecting a proper IMF component to extract a respiratory signal; the respiration rate signal is subtracted from the echo signal and the adaptive sliding energy time window is used to extract the heart rate signal, briefly as follows:
(1) the processed echo signal S is decomposed by CEEMD, and an appropriate IMF component is selected as a respiration signal SRAliasing the noisy cardiac signal x (n) ═ SH+vn＝S-SR；
(2) Fourier transform is carried out on the heart signal with the noise mixed, and the frequency with the maximum peak value in the frequency domain is taken as fHThe coarse average bixin interval is then calculated
(3) Performing relative energy calculation on the heart signal with aliasing noise by using long and short sliding time windows, wherein the width of the long window is Wl＝THWidth of short window WsThe reason for this is that the duration of the cardiac QRS wave is about 0.1s, so that the cardiac signal is well captured at 0.1s, and the coefficient signal c (n) of the relative energy is calculated as follows:
It should be noted that most of the existing filtering models use band-pass filtering or wavelet analysis, and the heart rate variability and the respiratory rate variability are smoothed along with the noise during processing, so that a good classification effect cannot be obtained due to the loss of features. While the present embodiment employs an adaptive sliding energy time window. The self-adaptation of the self-adaptive sliding energy time window is embodied in that the window width of the long window is self-adaptive. The sliding energy time window method is to suppress noise and improve the signal-to-noise ratio. Since the RR intervals are smoothed if the signal is filtered in the frequency domain, or using modern filters, and affect the characteristic signal.
Exemplarily, S13 specifically includes:
s130, calculating BB (break to break) intervals of each section of respiratory signal and HH (heart beat to heart beat) intervals of each section of cardiac signal in the signal samples; the BB interval refers to the time difference between adjacent peaks of the respiratory signal; the HH interval refers to the time difference between adjacent peaks of the cardiac signal.
S131, according to BB intervals of the multiple respiratory signals, obtaining respiratory variability features corresponding to the multiple respiratory signals.
And S132, obtaining heart rate variability characteristics corresponding to the multiple cardiac signals according to the HH interval of the multiple cardiac signals.
Exemplarily, the respiratory variability features in S131 comprise temporal, frequency, nonlinear domain features of respiratory variability; the heart rate variability features in S132 include time domain, frequency domain, nonlinear domain features of heart rate variability.
Exemplarily, S14 specifically includes:
s140, performing cross entropy analysis on the heart rate variability feature and the respiration variability feature to obtain similar features;
s141, removing the similar features between the heart rate variability features and the respiration variability features to obtain residual features;
and S142, performing principal component analysis on the residual features according to the KL divergence formula to obtain an optimal feature set.
In general, the respiratory variability features include time domain, frequency domain, nonlinear domain features of respiratory variability; the heart rate variability features include time domain, frequency domain, nonlinear domain features of heart rate variability.
Analyzing the characteristics of the obtained time domain, frequency domain and nonlinear domain of Heart Rate Variability (HRV) and respiratory variability (RRV) by cross Entropy (or called Relative Entropy analysis or KL Divergence Kullback-Leibler Divergence), and removing similar characteristics between the extracted characteristics of the two signals; and then, performing principal component analysis on the residual characteristics to achieve the effect of reducing the dimension.
KL divergence formula:
referring to fig. 2, the partition model is established by:
and calling the electrocardiogram annotation file, the breathing annotation file, the apnea annotation file and the sleep apnea annotation file in the MIT data set.
According to the electrocardio annotation file, the respiration annotation file, the apnea annotation file, the sleep apnea annotation file and a preset division interval, carrying out time re-division on the MIT data set, and dividing the MIT data set into a plurality of sections of data with sleep apnea labels or apnea labels; each piece of data has the same length as the division interval.
And calculating the time domain, frequency domain and nonlinear domain characteristics of the electrocardiosignals and the respiration signals in the MIT data set, and constructing a feature set.
And measuring the similarity between the features in the divided feature set by using cross entropy, if the similarity between the two features exceeds a first similarity threshold, reserving one of the two features, and then performing principal component analysis on the divided feature set.
And dividing the division characteristic set into a division training set and a division testing set.
And training the division training set by using machine learning algorithms of a hidden Markov model, a random forest and a CNN respectively, and performing weighted judgment on a result output by each machine learning algorithm by using a soft voting mode to obtain the division model.
It should be noted that the classification model shown in fig. 2 is a combination model of the partition model and the breathing model, and this combination model is equivalent to a classifier, which can perform classification analysis on the optimal feature set to obtain a sleep analysis result.
Referring to fig. 2, the process of establishing the breathing model is, for example:
the breath annotation file and apnea annotation file in the MIT dataset are invoked.
And according to the breathing interval preset by the breathing annotation file and the apnea annotation file, carrying out time repartition on the MIT data set, and dividing the MIT data set into a plurality of sections of data with apnea labels, wherein the length of each section of data is the same as the breathing interval.
And calculating the time domain, frequency domain and nonlinear domain characteristics of the respiratory signals in the MIT data set to construct a respiratory feature set.
And measuring the similarity between the features in the respiratory feature set by using cross entropy, if the similarity between the two features exceeds a second similarity threshold, reserving one of the two features, and then performing principal component analysis on the respiratory feature set.
And dividing the respiratory feature set into a respiratory training set and a respiratory testing set.
And training the breathing training set by using machine learning algorithms of a hidden Markov model, a random forest and a CNN respectively, and performing weighted judgment on a result output by each machine learning algorithm by using a soft voting mode to obtain the breathing model.
Another embodiment of the present application provides a non-contact sleep analysis apparatus, which includes a receiving module, a decomposition module, a division module, an extraction module, a dimension reduction module, and an analysis module.
The receiving module is used for receiving echo signals, eliminating direct current components and abnormal human body signals in the echo signals and obtaining superposed signals containing human body chest signals and heart front and back movement signals; the echo signal is obtained by transmitting an electromagnetic wave to the position of the thoracic cavity of the human body of the user by using an ultra-wideband radar;
the decomposition module is used for carrying out self-adaptive noise complete set empirical mode decomposition on the superposed signals to obtain respiratory signals and cardiac signals;
the dividing module is used for dividing the respiratory signal and the cardiac signal into a plurality of sections according to a preset time interval to obtain a signal sample containing the plurality of sections of respiratory signals and the plurality of sections of cardiac signals;
the extraction module is used for calculating respiratory variability features corresponding to the multiple segments of respiratory signals and heart rate variability features corresponding to the multiple segments of cardiac signals according to the signal samples;
the dimension reduction module is used for reducing dimensions of the respiratory variability feature and the heart rate variability feature to obtain an optimal feature set;
the analysis module is used for inputting the optimal feature set into a preset division model and a preset breathing model to obtain a sleep analysis result of the user; the sleep analysis result comprises sleep period division, abnormal sleep breathing state analysis and abnormal sleep breathing type analysis.
Another embodiment of the present invention is a computer-readable storage medium, which includes a stored computer program, where when the computer program runs, the apparatus in which the computer-readable storage medium is located is controlled to execute the method for non-contact sleep analysis according to the above embodiment.
Computer readable storage media for embodiments of the present invention may be computer readable signal media or computer readable storage media or any combination of the two. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM). Additionally, the computer-readable storage medium may even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (10)
1. A method of non-contact sleep analysis, comprising:
receiving echo signals, and eliminating direct current components and abnormal human body signals in the echo signals to obtain superposed signals containing human body chest signals and heart front and back movement signals; the echo signal is obtained by transmitting an electromagnetic wave to the position of the thoracic cavity of the human body of the user by using an ultra-wideband radar;
performing adaptive noise complete set empirical mode decomposition on the superposed signals to obtain respiratory signals and cardiac signals;
dividing the respiratory signal and the cardiac signal into a plurality of sections according to a preset time interval to obtain a signal sample containing a plurality of sections of respiratory signals and a plurality of sections of cardiac signals;
calculating respiratory variability features corresponding to the multiple segments of respiratory signals and heart rate variability features corresponding to the multiple segments of cardiac signals according to the signal samples;
performing dimension reduction on the respiratory variability feature and the heart rate variability feature to obtain an optimal feature set;
inputting the optimal feature set into a preset division model and a preset breathing model to obtain a sleep analysis result of the user; the sleep analysis result comprises sleep period division, abnormal sleep breathing state analysis and abnormal sleep breathing type analysis.
2. The method for non-contact sleep analysis according to claim 1, wherein the calculating a respiratory variability feature corresponding to the plurality of segments of respiratory signals and a heart rate variability feature corresponding to the plurality of segments of cardiac signals from the signal samples comprises:
calculating the BB interval of each segment of respiratory signal and the interval of each segment of cardiac signal in the signal sample; the BB interval refers to the time difference between adjacent peaks of the respiratory signal; the HH interval refers to a time difference between adjacent peaks of the cardiac signal;
obtaining respiratory variability features corresponding to the multiple respiratory signals according to BB intervals of the multiple respiratory signals;
and obtaining heart rate variability characteristics corresponding to the multiple segments of cardiac signals according to the HH intervals of the multiple segments of cardiac signals.
3. The method of contactless sleep analysis of claim 2, wherein the respiratory variability features include time domain, frequency domain, nonlinear domain features of respiratory variability; the heart rate variability features include time domain, frequency domain, nonlinear domain features of heart rate variability.
4. The method for analyzing sleep according to claim 1, wherein the receiving the echo signal, eliminating the dc component and the abnormal body signal in the echo signal, and obtaining the superimposed signal including the chest signal and the anterior-posterior heart movement signal comprises:
subtracting the echo signal from an average of the echo signal;
and carrying out data cleaning on the echo signals, and if the amplitude of part of the signals in the echo signals is larger than a preset filling threshold, randomly filling the part of the signals exceeding the threshold.
5. The method according to claim 1, wherein the performing adaptive noise-complete set empirical mode decomposition on the superimposed signal to obtain a respiratory signal and a cardiac signal comprises:
performing adaptive noise complete set empirical mode decomposition on the superposed signals, and selecting signal components to extract respiratory signals;
the respiration signal is subtracted from the echo signal, and a heart rate signal is extracted using an adaptive sliding energy time window.
6. The method of claim 1, wherein the dimensionality reduction of the respiratory variability feature and the heart rate variability feature to obtain an optimal feature set comprises:
performing cross entropy analysis on the heart rate variability features and the respiration variability features to obtain similar features;
removing the similar features between the heart rate variability feature and the respiration variability feature resulting in a remaining feature;
and performing principal component analysis on the remaining features according to a KL divergence formula to obtain an optimal feature set.
7. The non-contact sleep analysis method as claimed in claim 1, wherein the partition model is established by:
calling an electrocardio annotation file, a breath annotation file, an apnea annotation file and a sleep apnea annotation file in the MIT data set;
according to the electrocardio annotation file, the respiration annotation file, the apnea annotation file, the sleep apnea annotation file and a preset division interval, carrying out time re-division on the MIT data set, and dividing the MIT data set into a plurality of sections of data with sleep apnea labels or apnea labels; the length of each segment of data is the same as the division interval;
calculating time domain, frequency domain and nonlinear domain characteristics of the electrocardiosignals and the respiration signals in the MIT data set, and constructing a characteristic set for division;
measuring the similarity between the features in the divided feature set by using cross entropy, if the similarity between the two features exceeds a first similarity threshold, reserving one of the two features, and then performing principal component analysis on the divided feature set;
dividing the division characteristic set into a division training set and a division testing set;
and training the division training set by using machine learning algorithms of a hidden Markov model, a random forest and a CNN respectively, and performing weighted judgment on a result output by each machine learning algorithm by using a soft voting mode to obtain the division model.
8. The method of claim 1, wherein the breathing model is established by:
calling a breath annotation file and an apnea annotation file in the MIT data set;
according to the breathing interval preset by the breathing annotation file and the apnea annotation file, time subdivision is carried out on the MIT data set, the MIT data set is divided into multiple sections of data with apnea labels, and the length of each section of data is the same as that of the breathing interval;
calculating time domain, frequency domain and nonlinear domain characteristics of the breathing signals in the MIT data set, and constructing a breathing characteristic set;
measuring the similarity between the features in the respiratory feature set by using cross entropy, if the similarity between the two features exceeds a second similarity threshold, reserving one of the two features, and then performing principal component analysis on the respiratory feature set;
dividing the respiratory feature set into a respiratory training set and a respiratory testing set;
and training the breathing training set by using machine learning algorithms of a hidden Markov model, a random forest and a CNN respectively, and performing weighted judgment on a result output by each machine learning algorithm by using a soft voting mode to obtain the breathing model.
9. A non-contact sleep analysis device, comprising:
the receiving module is used for receiving the echo signals, eliminating direct current components and abnormal human body signals in the echo signals and obtaining superposed signals containing human body chest signals and heart front and back movement signals; the echo signal is obtained by transmitting an electromagnetic wave to the position of the thoracic cavity of the human body of the user by using an ultra-wideband radar;
the decomposition module is used for carrying out self-adaptive noise complete set empirical mode decomposition on the superposed signals to obtain respiratory signals and cardiac signals;
the dividing module is used for dividing the respiratory signal and the cardiac signal into a plurality of sections according to a preset time interval to obtain a signal sample containing the plurality of sections of respiratory signals and the plurality of sections of cardiac signals;
the extraction module is used for calculating respiratory variability features corresponding to the multiple segments of respiratory signals and heart rate variability features corresponding to the multiple segments of cardiac signals according to the signal samples;
the dimension reduction module is used for reducing dimensions of the respiratory variability feature and the heart rate variability feature to obtain an optimal feature set;
the analysis module is used for inputting the optimal feature set into a preset division model and a preset breathing model to obtain a sleep analysis result of the user; the sleep analysis result comprises sleep period division, abnormal sleep breathing state analysis and abnormal sleep breathing type analysis.
10. A computer-readable storage medium, comprising a stored computer program, wherein the computer program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the method of contactless sleep analysis according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110372729.1A CN113180596B (en) | 2021-04-07 | 2021-04-07 | Non-contact sleep analysis method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110372729.1A CN113180596B (en) | 2021-04-07 | 2021-04-07 | Non-contact sleep analysis method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113180596A true CN113180596A (en) | 2021-07-30 |
| CN113180596B CN113180596B (en) | 2024-02-06 |
Family
ID=76974843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110372729.1A Active CN113180596B (en) | 2021-04-07 | 2021-04-07 | Non-contact sleep analysis method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113180596B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114176521A (en) * | 2021-12-09 | 2022-03-15 | 森思泰克河北科技有限公司 | Sleep staging method and device based on radar information and terminal |
| CN114403892A (en) * | 2022-01-24 | 2022-04-29 | 中山大学 | Method, device and equipment for interactively adjusting respiratory feedback based on heart rate variability |
| AU2021107071B4 (en) * | 2021-08-24 | 2022-06-30 | Rudder Technology Pty Ltd | Radar based non-contact detection of sleep stage |
| CN115363598A (en) * | 2022-09-19 | 2022-11-22 | 深圳市太美亚电子科技有限公司 | Electrocardiosignal processing method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040249257A1 (en) * | 2003-06-04 | 2004-12-09 | Tupin Joe Paul | Article of manufacture for extracting physiological data using ultra-wideband radar and improved signal processing techniques |
| CN104873173A (en) * | 2015-05-19 | 2015-09-02 | 上海兆观信息科技有限公司 | Non-contact type sleep stage classification and sleep breathing disorder detection method |
| CN107920763A (en) * | 2015-07-16 | 2018-04-17 | 普瑞温迪克斯有限责任公司 | Handle biological data |
| CN108388912A (en) * | 2018-02-08 | 2018-08-10 | 南京理工大学 | Sleep stage method based on multisensor feature optimization algorithm |
| CN110659595A (en) * | 2019-09-10 | 2020-01-07 | 电子科技大学 | Tumble type and injury part detection method based on feature classification |
| CN111067503A (en) * | 2019-12-31 | 2020-04-28 | 深圳安视睿信息技术股份有限公司 | Sleep staging method based on heart rate variability |
-
2021
- 2021-04-07 CN CN202110372729.1A patent/CN113180596B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040249257A1 (en) * | 2003-06-04 | 2004-12-09 | Tupin Joe Paul | Article of manufacture for extracting physiological data using ultra-wideband radar and improved signal processing techniques |
| CN104873173A (en) * | 2015-05-19 | 2015-09-02 | 上海兆观信息科技有限公司 | Non-contact type sleep stage classification and sleep breathing disorder detection method |
| CN107920763A (en) * | 2015-07-16 | 2018-04-17 | 普瑞温迪克斯有限责任公司 | Handle biological data |
| CN108388912A (en) * | 2018-02-08 | 2018-08-10 | 南京理工大学 | Sleep stage method based on multisensor feature optimization algorithm |
| CN110659595A (en) * | 2019-09-10 | 2020-01-07 | 电子科技大学 | Tumble type and injury part detection method based on feature classification |
| CN111067503A (en) * | 2019-12-31 | 2020-04-28 | 深圳安视睿信息技术股份有限公司 | Sleep staging method based on heart rate variability |
Non-Patent Citations (2)
| Title |
|---|
| 冯静达等: "基于心率和呼吸特征结合的睡眠分期研究", 航天医学与医学工程, vol. 33, no. 2, pages 152 - 128 * |
| 郑红梅等: "基于FCEEMD 的心跳信号和呼吸信号分离研究", 电子测量与仪器学报, vol. 31, no. 11, pages 1809 - 1814 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2021107071B4 (en) * | 2021-08-24 | 2022-06-30 | Rudder Technology Pty Ltd | Radar based non-contact detection of sleep stage |
| CN114176521A (en) * | 2021-12-09 | 2022-03-15 | 森思泰克河北科技有限公司 | Sleep staging method and device based on radar information and terminal |
| CN114176521B (en) * | 2021-12-09 | 2022-07-01 | 森思泰克河北科技有限公司 | Sleep staging method and device based on radar information and terminal |
| CN114403892A (en) * | 2022-01-24 | 2022-04-29 | 中山大学 | Method, device and equipment for interactively adjusting respiratory feedback based on heart rate variability |
| CN114403892B (en) * | 2022-01-24 | 2024-04-02 | 中山大学 | Method, device and equipment for interactively adjusting respiratory feedback based on heart rate variability |
| CN115363598A (en) * | 2022-09-19 | 2022-11-22 | 深圳市太美亚电子科技有限公司 | Electrocardiosignal processing method and system |
| CN115363598B (en) * | 2022-09-19 | 2023-03-24 | 深圳市太美亚电子科技有限公司 | Electrocardiosignal processing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113180596B (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113180596B (en) | Non-contact sleep analysis method, device and storage medium | |
| US7225013B2 (en) | Adaptive prediction of changes of physiological/pathological states using processing of biomedical signals | |
| JP4278048B2 (en) | Wavelet-based analysis of pulse oximetry signals | |
| Lestari et al. | Wavelet based-analysis of alpha rhythm on eeg signal | |
| Erdamar et al. | A wavelet and teager energy operator based method for automatic detection of K-Complex in sleep EEG | |
| KR101868888B1 (en) | Classification of Sleep/Wakefulness using Nasal Pressure for Patients with Sleep-disordered Breathing | |
| KR102237466B1 (en) | Sleep stage classification device and method using pulse oximeter | |
| WO2006054306A2 (en) | Sleep staging based on cardio-respiratory signals | |
| Sameni et al. | Model-based Bayesian filtering of cardiac contaminants from biomedical recordings | |
| CN114781465B (en) | rPPG-based non-contact fatigue detection system and method | |
| TİMUŞ et al. | k-NN-based classification of sleep apnea types using ECG | |
| Zheng et al. | Human emotional stress assessment through Heart Rate Detection in a customized protocol experiment | |
| CN112089413A (en) | Blocking type sleep apnea syndrome screening system | |
| Sivaranjni et al. | Detection of sleep apnea through ECG signal features | |
| CN111449622A (en) | Atrial fibrillation recognition system based on BCG detection | |
| Espiritu et al. | Automated detection of sleep disorder-related events from polysomnographic data | |
| Robles-Rubio et al. | A new movement artifact detector for photoplethysmographic signals | |
| Motin et al. | PPG derived respiratory rate estimation in daily living conditions | |
| Rivolta et al. | Effects of the series length on Lempel-Ziv Complexity during sleep | |
| Khavas et al. | Robust heartbeat detection using multimodal recordings and ECG quality assessment with signal amplitudes dispersion | |
| Horng et al. | Personal identification via heartbeat signal | |
| Alfarhan et al. | Automated electrocardiogram signals based risk marker for early sudden cardiac death prediction | |
| Li et al. | Feature Selection for the Detection of Sleep Apnea using Multi-Bio Signals from Overnight Polysomnography | |
| Yu et al. | Feature extraction of vigilance level based on heart rate variability of electrocardiogram | |
| Chang et al. | Pulse rate derivation and its correlation with heart rate |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |